© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 8422
    Prev
    Next
    INDEX
    Explanations

    events and actions involving mutual dependencies and interactions between entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AutoScaleMode
    -0.81
    toPromise
    -0.55
    ThemeOverlay
    -0.54
    Ambos
    -0.52
     Bioaccumulative
    -0.51
    StackNavigator
    -0.51
    bujete
    -0.49
    一切
    -0.45
    umą
    -0.45
     måneder
    -0.44
    POSITIVE LOGITS
     each
    4.36
    each
    3.51
    Each
    3.20
     Each
    3.20
     EACH
    2.83
    EACH
    2.68
     ciascuno
    2.38
     chacun
    2.37
     ciasc
    2.28
     chacune
    2.27
    Activations Density 1.041%

    No Known Activations